debug
Comprehensive debugging toolkit for complex issues - diagnosis, reproduction, log analysis, performance, and memory debugging
Best use case
debug is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Comprehensive debugging toolkit for complex issues - diagnosis, reproduction, log analysis, performance, and memory debugging
Teams using debug should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/debug/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How debug Compares
| Feature / Agent | debug | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Comprehensive debugging toolkit for complex issues - diagnosis, reproduction, log analysis, performance, and memory debugging
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Debug Skill - Advanced Debugging Operations You are routing requests to specialized debugging operations. Parse the `$ARGUMENTS` to determine which debugging operation to execute. ## Available Operations - **diagnose** - Comprehensive diagnosis and root cause analysis across all stack layers - **reproduce** - Create reliable reproduction strategies and test cases for issues - **fix** - Implement targeted fixes with verification and prevention measures - **analyze-logs** - Deep log analysis with pattern detection and timeline correlation - **performance** - Performance debugging, profiling, and optimization - **memory** - Memory leak detection, analysis, and optimization ## Routing Logic Extract the first word from `$ARGUMENTS` as the operation name, and pass the remainder as operation parameters. **Arguments received**: `$ARGUMENTS` **Routing Instructions**: 1. **Parse the operation**: Extract the first word from `$ARGUMENTS` 2. **Load operation instructions**: Read the corresponding operation file from `.claude/commands/debug/` 3. **Execute with context**: Follow the operation's instructions with the remaining parameters 4. **Leverage agent**: All operations can leverage the 10x-fullstack-engineer agent for deep expertise ## Operation Routing ``` diagnose → Read and follow: .claude/commands/debug/diagnose.md reproduce → Read and follow: .claude/commands/debug/reproduce.md fix → Read and follow: .claude/commands/debug/fix.md analyze-logs → Read and follow: .claude/commands/debug/analyze-logs.md performance → Read and follow: .claude/commands/debug/performance.md memory → Read and follow: .claude/commands/debug/memory.md ``` ## Base Directory All operation files are located at: `.claude/commands/debug/` ## Error Handling If no operation is specified or the operation is not recognized: **Available debugging operations**: - `/debug diagnose issue:"..." [environment:"..."] [logs:"..."]` - Comprehensive diagnosis - `/debug reproduce issue:"..." [environment:"..."] [data:"..."]` - Create reproduction strategy - `/debug fix issue:"..." root_cause:"..." [verification:"..."]` - Implement targeted fix - `/debug analyze-logs path:"..." [pattern:"..."] [timeframe:"..."]` - Deep log analysis - `/debug performance component:"..." [metric:"..."] [threshold:"..."]` - Performance debugging - `/debug memory component:"..." [symptom:"..."] [duration:"..."]` - Memory debugging **Example usage**: ``` /debug diagnose issue:"Users getting 500 errors on file upload" environment:"production" logs:"logs/app.log" /debug reproduce issue:"Payment webhook fails intermittently" environment:"staging" data:"sample-webhook-payload.json" /debug fix issue:"Race condition in order processing" root_cause:"Missing transaction lock" verification:"run-integration-tests" /debug analyze-logs path:"logs/application.log" pattern:"ERROR.*timeout" timeframe:"last-24h" /debug performance component:"api-endpoint:/orders" metric:"response-time" threshold:"200ms" /debug memory component:"background-worker" symptom:"growing-heap" duration:"6h" ``` Please specify an operation and provide the necessary parameters. ## Integration with 10x-fullstack-engineer Agent All debugging operations are designed to work seamlessly with the 10x-fullstack-engineer agent, which provides: - Cross-stack debugging expertise - Systematic root cause analysis - Production-grade debugging strategies - Performance and security awareness - Prevention-focused mindset ## Execution Based on the parsed operation from `$ARGUMENTS`, read the appropriate operation file and follow its instructions with the remaining parameters.
Related Skills
specification-writing
Core reference for EARS requirement patterns, Given/When/Then acceptance criteria, RFC 2119 language, requirement ID conventions, and specification quality checklists. Background knowledge for the spec-writer agent. Preloaded by spec-writer via the skills frontmatter field; not user-invocable.
refine
Unified specification refinement plugin. Single entry point for all spec operations: greenfield architecture pipelines (principles → design → stack → spec → plan), feature spec creation in existing systems, iterative convergence loops, quality reviews, drift detection, finalization, ticket decomposition, traceable updates, and lifecycle archival. Detects pipeline state from existing artifact frontmatter and routes intelligently. Use whenever you need to create, refine, validate, or evolve a technical specification.
validation-orchestrator
Intelligent validation orchestrator with auto-detection and progressive validation workflows
security-scan
Comprehensive security scanning for secrets, vulnerabilities, and unsafe practices
schema-validation
Validate JSON schemas, required fields, and format compliance for marketplaces and plugins
quality-analysis
Deep quality analysis with scoring, recommendations, and actionable reports
documentation-validation
Validate documentation completeness, format, and quality for plugins and marketplaces
best-practices
Enforce OpenPlugins and Claude Code best practices for naming, versioning, and standards compliance
message-generation
Generate conventional commit messages following best practices
history-analysis
Analyze git history to learn project's commit style and conventions
commit-error-handling
Handle git errors and edge cases gracefully
commit-best-practices
Enforce git commit best practices and workflow guidance